Latest Posts

by Synced 2017-08-01 Number of comments0

Research

Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models

The paper proposes a hybrid neural machine translation model concerning both words and characters, which mainly contributes to the translation of rare or unknown words.

by Synced 2017-07-31 5

Conference Global News Industry

One Night at CVPR 2017 : Exploring IJCV and the Asia Research Force

Hosted annually in the United States, the Computer Vision and Pattern Recognition Conference received 2,620 submissions, accepted 783 papers, attracted 127 sponsors with $859,000 in sponsorship and close to 5,000 attendees.

by Synced 2017-07-30 Number of comments0

Research

PixelGAN Autoencoders

PixelGAN is an autoencoder for which the generative path is a convolutional autoregressive neural network on pixels, conditioned on a latent code, and the recognition path uses a generative adversarial network (GAN) to impose a prior distribution on the latent code.

by Synced 2017-07-28 9

AI Globalization EU & UK Global News Industry

Canvassing Switzerland’s AI Landscape

We explore top-notch Swiss AI facilities: starting with deep learning and neural network research at IDSIA in Lugano, to interdisciplinary research at École Polytechnique Fédérale de Lausanne and University of Basel, and ending with robotics innovations at ETH in Zurich and University of Zurich.

by Synced 2017-07-26 Number of comments0

Research

Learning to Map Vehicles into Bird’s Eye View

This paper presents a deep learning architecture to map the vehicle detection in the frontal view onto a bird’s eye view of the road scene, while preserving the size and direction of the moving vehicle.

by Synced 2017-07-25 1

Industry

Amazon is Building its Grocery Empire

Most categories have been taken over by e-commerce yet the category of fresh groceries hasn’t been disrupted by online.

by Synced 2017-07-24 Number of comments0

Research

Generalizing and Hybridizing Count-based and Neural Language Model

This paper demonstrates a framework called Mixture Of Distribution Language Models (MODLMs), which provides a single mathematical framework that encompasses several widely used classes of LMs.

by Synced 2017-07-22 2

Global News

Relearn the Linguistic World in “Arrival”: An Interview with Jessica Coon

Computer science and machine learning scholars are increasingly interested in languages, and natural language processing has shown great progress as a result.

by Synced 2017-07-21 1

Research

Kullback-Leibler Divergence Explained

Minimization of the KL-divergence can be thought of as maximizing the likelihood ratio, which appears in numerous applications.

by Synced 2017-07-20 2

Industry Research

Apple is in a Dilemma on iPhone’s 10-year-old Birthday

Apple is confused about what its next big thing will be.

by Synced 2017-07-19 Number of comments0

Research

Navigating Intersections with Autonomous Vehicles using Deep Reinforcement Learning

One crucial standard in measuring autonomous vehicles is whether the autonomous vehicles can go through intersections with no signals. In this paper, the authors provide us with a new strategy of using Deep Reinforcement Learning.

by Synced 2017-07-18 3

Community Research

Applying Data Science to Robotics

In his blog post “How Data Science Apply to Robotics” on Data Science Central, Dr. Ammar A. Raja points out that there are two major problems scientists have encountered while applying data science to robotics.

by Synced 2017-07-17 3

Research

Applying Multinomial Naive Bayes to NLP Problems: A Practical Explanation

Bayes’ Theorem is useful for dealing with conditional probabilities, since it provides a way for us to reverse them.

by Synced 2017-07-14 2

Research

Email Category Prediction

By accurately predicting the category of an email, we can better extract useful information from it according to its corresponding templates.

by Synced 2017-07-12 3

Research

A Rational Analysis of Curiosity

Curiosity is related to the field of intrinsic motivation, and is recognized as a factor in a wide range of human endeavour.

by Synced 2017-07-11 Number of comments0

Research

Massive Exploration of Neural Machine Translation Architectures

Although no innovations for the NMT architecture was introduced, the authors claim that a classic NMT baseline system with carefully tuned hyperparameters can still achieve comparable result to the state-of-the-art.

by Synced 2017-07-10 Number of comments0

Community Conference GMIS 2017

Jürgen Schmidhuber: True Artificial Intelligence Will Change Everything

From LSTM deep learning technique to self-learning humanoid robot, Jürgen Schmidhuber’s research teams have won awards in various machine learning competitions, including medical image recognition.

by Synced 2017-07-07 Number of comments0

Research

Exploiting Source-side Monolingual Data in Neural Machine Translation

Instead of exploring target-side monolingual data for NMT, the author of this paper proposes two novel methods for source-side monolingual data exploration.

by Synced 2017-07-06 2

AI Global News

Lethal Autonomous Weapons & Info-Wars: A Scientist’s Warning

“To pretend science is morally neutral, and that you can develop anything and have clean hands because it is someone else using it to kill people is extremely naive, and scientists should know that.” – UC Berkeley’s Dr. Stuart Russell

by Synced 2017-07-05 1

Industry Research

Giving Robots a Sense of Touch

The rubber on GelSight sensor will conform to any object pressed against it, resulting in the reflective lights on the metallic paint to vary according to different materials and shapes.

by Synced 2017-07-04 Number of comments0

Research

Appearance-Based Gaze Estimation in the Wild

Multimodal convolutional neural networks for appearance-based gaze estimation that significantly outperforms state-of-the-art methods in the most challenging cross-dataset evaluation

by Synced 2017-07-03 Number of comments0

Research

Using Human Brain Activity to Guide Machine Learning

Instead of investigating what steps the brain takes to process information, the authors of this paper link brain activity directly to the learning process.

by Synced 2017-07-01 3

China Conference GMIS 2017 Research

Gary Marcus: The Road to Artificial General Intelligence

Gary Marcus the Professor of Psychology at New York University, CEO and Founder of Geometric Intelligence, speaks at GMIS 2017.

by Synced 2017-06-30 Number of comments0

Research

Understanding the Mechanisms of Deep Transfer Learning for Medical Images

This paper systematically studies how a convolutional neural network, trained on ImageNet for image classification tasks, works on medical images – or more precisely on ultrasound images – for the “Kidney Detection” problem.

by Synced 2017-06-29 1

Research

Tensorflow Programs and Tutorials

This repository did some toy experiments based on Tensorflow in order to introduce some deep learning concepts which are used for image recognition and language modeling.

by Synced 2017-06-28 Number of comments0

Research

Deep Learning with Dynamic Computation Graphs

Google introduced a new algorithm: ‘Dynamic Batching’, and developed a Tensorflow-based library called ‘TensorFlow Fold’, which solved the DCGs problem in both theoretical and empirical fields.

by Synced 2017-06-27 7

AI Research

Conversational Systems: A General Review

How can we communicate with “super intelligent” robots? The answer lies in conversational systems.

by Synced 2017-06-26 2

Community Research

Global AI Hackathon in Toronto

On June 23-24, the first Global Artificial Intelligence Hackathon took place in Toronto at University of Toronto, alongside 14 otherContinue Reading

by Synced 2017-06-26 1

AI Research

A Survey of Question Answering for Math and Science Problem

Overview of the ways to make a machine smart enough to pass the standardized math and science test.

by Synced 2017-06-23 5

AI Globalization Global News Industry US & Canada

Building AI Superclusters in Canada

Canada is determined to build AI superclusters in Toronto-Waterloo, Montréal, and Edmonton.

by Synced 2017-06-21 Number of comments0

Research

L2-constrained Softmax Loss for Discriminative Face Verification

Softmax loss has become a standard build-in loss function for a lot of mathematical tools like TensorFlow, Torch and Caffe. It is mainly used for classification and has its advantages and disadvantages, the latter of which is the focus of this paper.

by Synced 2017-06-16 3

Industry Research

Deep Learning Paper Sparks Online Feud!

A tweet from Google DeepMind’s Nenad Tomasev, concerning a paper from the prestigious Montreal Institute for Learning Algorithms has sparked a well-known natural language processing expert Yoav Goldberg to tweet back: “…I really dislike this work.”

by Synced 2017-06-14 Number of comments0

AI Research

Failures of Deep Learning

In 2015, Anh Nguyen published a paper in CVPR that identified a limit in computer vision, where you can fool a deep neural network (DNN) by changing an image in a way that’s imperceptible to humans, but can cause the DNN to label the image as something else entirely.

by Synced 2017-06-13

Conference

Scientists and Stakeholders in Geneva for Good Artificial Intelligence

“AI for Good Global Summit,” held June 7-9 in Geneva, Switzerland.

by Synced 2017-06-13 3

AI Chinese AI Talent in US Industry United States

Ready, Set, Go! Meet Yuandong Tian: AI Maverick

“Scientists need passion to do research, and that is my passion.” – Yuandong Tian, Facebook Artificial Intelligence Researcher

by Synced 2017-06-12 2

Industry Research

Epic’s Tim Sweeney: Deep Learning A.I. Will Open New Frontiers in Game Design

Tim Sweeney predicts that video game companies will ultimately utilize advanced AI techniques when the VR/AR games (or so-called “The Metaverse” games) become popular, due to advancements of cameras and displays

by Synced 2017-06-10 Number of comments0

Research

How to Teach Machines to Think Like Humans

Google’s DeepMind introduced its Relation Network (RN) module and a Visual Interaction Network (VIN) that achieved superhuman performance in specific tests by employing a different type of reasoning concerning objects and physical interactions.

by Synced 2017-06-09 5

Research

Does Fitness Data Make the Average Person Healthier?

With these handy wearable gadgets, we can now track every aspect of our health and fitness. But are they actually making a difference to the average person’s well being?

by Synced 2017-06-08 Number of comments0

Research

Adversarial Generator-Encoder Networks

New autoencoder-like generative network, called Adversarial Generator-Encoder Networks (AGE Network), does not have any discriminators, which makes the entire architecture much simpler than some recently-proposed GANs, but with nearly the same-level performance

by Synced 2017-06-07 Number of comments0

Community United States

2017 1000 Plan Startup Contest – Silicon Valley Regional Competition

1000 Plan Startup Contest is going to hit Silicon Valley on June 10. As one of the most influential US-ChinaContinue Reading